Selected Publications

Wildfires constitute an important threat to human lives and livelihoods worldwide, as well as a major ecological disturbance. However, available wildfire databases often provide incomplete or inaccurate information, namely regarding the timing and extension of fire events. In this study, we described a generic framework to compare, rank and combine multiple remotely-sensed indicators of wildfire disturbances, in order to not only select the best indicators for each specific case, as well as to provide multi-indicator consensus approaches that can be used to detect wildfire disturbances in space and time. [open to see the full abstract]
In JAG, 2019
PDF Source Document

Geographic Object-based Image Analysis (GEOBIA) is increasingly used to process high-spatial resolution imagery, with applications ranging from single species detection to habitat and land cover mapping. Image segmentation plays a key role in GEOBIA workflows, allowing to partition images into homogenous and mutually exclusive regions. Nonetheless, segmentation techniques require a robust parameterization to achieve the best results. Frequently, inappropriate parameterization leads to sub-optimal results and difficulties in comparing distinct methods. Here, we present an approach based on Genetic Algorithms (GA) to optimize image segmentation parameters by using the performance scores from object-based classification, thus allowing to assess the adequacy of a segmented image in relation to the classification problem. This approach was implemented in a new R package called SegOptim, in which several segmentation algorithms are interfaced, mostly from open-source software (GRASS GIS, Orfeo Toolbox, RSGISLib, SAGA GIS, TerraLib), but also from proprietary software (ESRI ArcGIS). SegOptim also provides access to several machine-learning classification algorithms currently available in R, including Gradient Boosted Modelling, Support Vector Machines, and Random Forest. [open to see the full abstract]
In JAG, 2019
PDF

Here we describe how satellite-derived Ecosystem Functional Attributes (EFAs), which offer a more integrative and faster evaluation of ecosystem responses to environmental change, can be used as predictors in Species Distribution Models (SDMs) and for implementing multi-scale species monitoring programs. [open to see the full abstract]
In PLoS One, 2018
PDF

In this paper we describe a framework to evaluate post-fire recovery based on remotely-sensed measures of relative vegetation recovery, calculated from satellite NDVI time-series. Three indicators are proposed: the novel Cumulative Relative Recovery Index (CRRI), the Recovery Trend Index (RTI), and the Half Recovery Time index (HRT). Based on the proposed indicators, we investigated main factors driving post-fire dynamics with a set of Random Forest models. [open to see the full abstract]
In ECOLIND, 2018
PDF

We focus on Mediterranean wetlands in central Iberia and perform a multi-level, comparative study of two endemic pond-breeding amphibians, a salamander (Pleurodeles waltl) and a toad (Pelobates cultripes) and identified major factors associated with population connectivity through the analysis of three sets of variables potentially affecting gene flow at increasingly finer levels of spatial resolution. Overall, results suggest a positive role of structural heterogeneity in population connectivity in pond-breeding amphibians, with habitat patches of Mediterranean scrubland and open oak woodlands (“dehesas”) facilitating gene flow. [open to see the full abstract]
In Molecular Ecology, 2017
PDF

In this work we assessed the vulnerability of herptile species to future climate and land use changes in fragmented landscapes. We developed and tested a methodological approach combining the strengths of Species Distribution Models (SDMs) and of functional connectivity analysis. [open to see the full abstract]
In Ecological Complexity, 2016
PDF

In this paper we explored how satellite-based environmental variables can be fed into species distribution models (SDMs) to investigate species-environment relations and forecast responses to change. We address the spatiotemporal dynamics of species’ habitat suitability at the landscape level by combining multi-temporal RS data with SDMs for analysing inter-annual habitat suitability dynamics. [open to see the full abstract]
In Biodiversity & Conservation, 2016
PDF

In this work we evaluated how very high-resolution colour imagery and digital surface models from an unmanned aerial vehicle can be effectively used for assessing habitat extent and condition in fine-scale disturbance-dependent mountain mosaics. [open to see the full abstract]
In Applied Vegetation Science, 2015
PDF

Recent Publications

More Publications

. Mapping Spatial Patterns and Recent Changes in Quercus pyrenaica (Willd.) Forests Using Remote Sensing and Machine Learning. In Remote Sensing, 2026.

Source Document

. Combined impacts of invasive alien species and fire on ecosystems are complex, mostly negative, and understudied: a global review. In bioRxiv, 2026.03. 08.7103552026, 2026.

Source Document

. Exploring turnover dynamics in Iberian Oak forests under climate change scenarios. In Discover Conservation, 2026.

Source Document

. Tracking submediterranean ecotone shifts under climate change scenarios using marcescent oaks as indicators. In Scientific Reports, 2025.

Source Document

. Climate-Driven Habitat Shifts and Conservation Implications for the Submediterranean Oak Quercus pyrenaica Willd.. In Forests, 2025.

Source Document

. Open Access to Burn Severity Data—A Web-Based Portal for Mainland Portugal. In Fire, 2025.

Source Document

. Fostering Post-Fire Research Towards a More Balanced Wildfire Science Agenda to Navigate Global Environmental Change. In Fire, 2025.

Source Document

. Landscape functioning in reservoir water quality prediction: Current use and predictive capacity. In Ecohydrology, 2024.

Source Document

. How can landscape visual assessment inform landscape planning and management?–Alto Douro Wine region case study, Portugal. In Applied Geography, 2024.

Source Document

. Macroclimatic niche similarity and species relatedness shift their influence on species co‐occurrence in bryophyte forest communities across scales. In Journal of Ecology 113 (6), 1546-15591 2025, 2024.

Source Document

Recent Posts

1 min read

A curated list of useful resources in Remote Sensing / Earth Observation

CONTINUE READING

R-packages

R packages developed for ecological, remote sensing, and geospatial analysis

All Object-Based Image Analysis Machine Learning Species Distribution Models Connectivity Thermal Imaging

SegOptim

A R package for running Object-based Image Analysis and optimizing image segmentation parameters.

ThermalRaster

R package for handling thermal and RGB images from FLIR cameras.

rsegm

“Classical” object-based image segmentation (OBIA) for geospatial data.

SDMconnect

R toolkit for raster-based connectivity analyses using Species Distribution Models as inputs.

Datasets

Open data products released alongside research and projects

All Burn Severity Invasive Species Climate Land Cover

CHELSA Future Climate Predictors for SDMs - OneSTOP Task 5.1

Future CHELSA v2.1 BIOCLIM+ bioclimatic and environmental predictor datasets for species distribution model projections under SSP1-2.6, SSP3-7.0, and SSP5-8.5 for 2041-2070 and 2071-2100. Released under the OneSTOP Project (Task 5.1).

Reclassified Global Land-Cover Plant Functional Type Dataset (1 km) — OneSTOP Task 5.1

Reclassified global land-cover Plant Functional Type (PFT) dataset at 1 km resolution for the baseline year (2015) and future SSP/RCP scenarios, derived from Chen et al. (2022, DOI:10.1038/s41597-022-01208-6). Released under the OneSTOP Project (Task 5.1).

CHELSA Bioclimatic & Environmental Predictors for SDMs — OneSTOP Baseline (1981–2010)

CHELSA bioclimatic and environmental predictors prepared for species distribution models under the OneSTOP Project (Task 5.1). Historical baseline covering 1981–2010.

Cortaderia selloana UAV occurrences (mainland Portugal, 2019–2020)

Georeferenced occurrence records of Cortaderia selloana (pampas grass) across mainland Portugal (2019–2020) obtained from UAV-based surveys under the LIFE STOP CORTADERIA project (LIFE17 NAT/ES/000495).

SeverusPT

A multi-source burn severity dataset for mainland Portugal, integrating Landsat and Sentinel-2 imagery to support post-fire monitoring, recovery assessment, and ecological research.

Earth-Engine apps

Interactive Google Earth Engine applications for remote sensing, fire assessment, and rapid environmental impact analysis

This section gathers web applications I have developed with Google Earth Engine to make satellite-based environmental analysis available through public, interactive interfaces. These apps focus on operational workflows where users need to inspect an event, define an area of interest, compare satellite observations through time, and export or interpret results without having to write Earth Engine code.

All Burn Severity Fire Recovery Storm Impact

Burn Severity Analyst

A Google Earth Engine app for plotting satellite time series over burned areas or custom areas of interest to assess fire severity and post-fire recovery.

Burn Severity Mapper

A SeverusPT Google Earth Engine app for generating burn severity maps from pre- and post-fire Sentinel-2 or Landsat imagery.

Preliminary Assessment of Storm Kristin Impacts

A Google Earth Engine app for preliminary remote-sensing assessment of the impacts of Storm Kristin in Portugal.

Tags

Contact

  • joaofgo@gmail.com
  • +351 252 660 411
  • CIBIO - Research Center in Biodiversity and Genetic Resources, Campus Agrário de Vairão, R. Padre Armando Quintas, nr 7 - 4485-661 Vairão, V. Conde, Portugal
  • 10h - 18h | email me for an appointment